SLR automates creation of inductive logic tasks and a 20-level curriculum benchmark to train and evaluate LLM reasoning, yielding doubled accuracy for Llama-3-8B and generalization to other benchmarks.
Preprint
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations focus on tasks complexifications, for which human also struggle to maintain performances, no evaluation has been performed on tasks simplifications. To tackle this issue, we introduce HackAtari, a set of task variations of the Arcade Learning Environments. We use it to demonstrate that, contrary to humans, RL agents systematically exhibit huge performance drops on simpler versions of their training tasks, uncovering agents' consistent reliance on shortcuts. Our analysis across multiple algorithms and architectures highlights the persistent gap between RL agents and human behavioral intelligence, underscoring the need for new benchmarks and methodologies that enforce systematic generalization testing beyond static evaluation protocols. Training and testing in the same environment is not enough to obtain agents equipped with human-like intelligence.
representative citing papers
VAORA aligns VLM chain-of-thought reasoning with visual scene observations and post-action outcomes via structured symbolic rewards, achieving cross-task and cross-environment generalization on physical reasoning benchmarks.
GRAIL autonomously grounds relational concepts in NeSy-RL by using LLM weak supervision followed by interaction-based refinement, matching or exceeding manually defined concepts on Atari games.
ActivationReasoning grounds logical reasoning in LLM latent activations via SAEs to enable structured inference, concept composition, and behavior steering on multi-hop, abstraction, and safety tasks.
citing papers explorer
-
SLR: Automated Synthesis for Scalable Logical Reasoning
SLR automates creation of inductive logic tasks and a 20-level curriculum benchmark to train and evaluate LLM reasoning, yielding doubled accuracy for Llama-3-8B and generalization to other benchmarks.
-
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
VAORA aligns VLM chain-of-thought reasoning with visual scene observations and post-action outcomes via structured symbolic rewards, achieving cross-task and cross-environment generalization on physical reasoning benchmarks.
-
GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
GRAIL autonomously grounds relational concepts in NeSy-RL by using LLM weak supervision followed by interaction-based refinement, matching or exceeding manually defined concepts on Atari games.
-
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
ActivationReasoning grounds logical reasoning in LLM latent activations via SAEs to enable structured inference, concept composition, and behavior steering on multi-hop, abstraction, and safety tasks.